EngineX-Mthreads/enginex-mthreads-llama.cpp
4
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Revert "sync from b7516"

Browse Source 
This reverts commit 6ee41dd9e3.
This commit is contained in:
xiezhongtao
2026-01-16 11:34:48 +08:00
parent 6ee41dd9e3
commit 620f04050b
380 changed files with 38842 additions and 18471 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/sycl/run-llama2.sh
View File

@@ -22,9 +22,9 @@ if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
else
#use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT}
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT}
fi